Skip to content

Add vimin-core — self-hostable distributed LLM/Whisper inference orchestration#8

Open
pberlizov wants to merge 1 commit into
av:mainfrom
pberlizov:add-vimin-core
Open

Add vimin-core — self-hostable distributed LLM/Whisper inference orchestration#8
pberlizov wants to merge 1 commit into
av:mainfrom
pberlizov:add-vimin-core

Conversation

@pberlizov
Copy link
Copy Markdown

What is vimin-core?

vimin-core is a self-hostable Python backend for orchestrating local LLM and Whisper inference across a fleet of up to 10 machines.

Why it fits here:

  • Fully self-hosted — no cloud, no external API calls, no telemetry
  • MLX on Apple Silicon, llama.cpp on any platform
  • Exposes a simple HTTP API for broadcast and multi-step pipeline execution
  • Dashboard UI included
  • MIT license

Added to the Backends section.

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant